{"id":"W4285817857","doi":"10.1093/gigascience/giac065","title":"Toward global integration of biodiversity big data: a harmonized metabarcode data generation module for terrestrial arthropods","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Horizon 2020 Framework Programme; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Fundación Bancaria Caixa d'Estalvis i Pensions de Barcelona; European Commission","keywords":"Big data; Biodiversity; Computer science; Data science; Data integration; Ecology; Data mining; Biology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000800956,0.0001326022,0.0001711081,0.00002755999,0.0007838274,0.0000354662,0.00206349,0.0000262092,0.0002226403],"category_scores_gemma":[0.000144367,0.0001321735,0.00004400054,0.0003829047,0.0006857951,0.0007808236,0.00640043,0.0000809977,0.00004043357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000315979,"about_ca_system_score_gemma":0.00001814606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001178936,"about_ca_topic_score_gemma":0.0003232016,"domain_scores_codex":[0.9979577,0.00009254009,0.0002103542,0.0008096744,0.0006822319,0.0002474887],"domain_scores_gemma":[0.9987468,0.00003073548,0.0001612348,0.0009917674,0.000005288983,0.00006418262],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004566218,0.0010914,0.4437429,0.00002131477,0.0001263266,0.00001596265,0.001794079,0.006856032,0.2602854,0.0001148152,0.16087,0.1246251],"study_design_scores_gemma":[0.008144665,0.00176033,0.5367352,0.00001690393,0.0006362716,0.000043889,0.006481769,0.2736988,0.05118368,0.001146125,0.1182714,0.001880991],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9516013,0.00009506088,0.03627222,0.0009581491,0.001399684,0.0007154457,0.008741363,0.00003854222,0.0001781891],"genre_scores_gemma":[0.9603748,0.00005621096,0.03789804,0.0001801803,0.00007551238,0.00001735062,0.001340985,0.000003168088,0.00005369698],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2668428,"threshold_uncertainty_score":0.7977678,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2371889043425931,"score_gpt":0.2950674986009877,"score_spread":0.05787859425839459,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}